Methods and Apparatus for Detecting and Recognizing Graphical Character Representations in Image Data Using Symmetrically-Located Blank Areas

1. A method of identifying a candidate region in image data, the method comprising: detecting, using a processor, blank areas in the image data; identifying, using the processor, a symmetrically-located pair of the blank areas; and designating an area of the image data between the symmetrically-located pair of the blank areas as a candidate region for an image processing function.

2. A method as defined in claim 1 , wherein detecting the blank areas in the image data comprises: detecting edges in the image data; and designating portions of the image data that are edges as blank.

3. A method as defined in claim 1 , wherein identifying the symmetrically-located pair of the blank areas comprises: comparing a first dimension of a first one of the blank areas to a second dimension of a second one of the blank areas; comparing a first distance of the first blank area from a center axis of the image data to a second distance of the second blank area from the center axis; and identifying the first and second ones of the blank areas as the symmetrically-located pair if: the first dimension is substantially similar to the second dimension; and the first distance is substantially similar to the second distance.

4. A method as defined in claim 1 , further comprising: counting a number of edges in a space between the blank areas of the symmetrically-located pair; comparing the number of edges to a threshold; and discarding the symmetrically-located pair when the number of edges does not meet the threshold.

5. A method as defined in claim 1 , further comprising fitting a bounding box around the candidate region.

6. A method as defined in claim 1 , wherein detecting the blank areas in the image data comprises: grouping continuous blank pixels into horizontal lines; and grouping ones of the horizontal lines having a similar characteristic.

7. A method as defined in claim 1 , wherein the image processing function is a character recognition operation.

8. An apparatus for identifying a candidate region in image data, the apparatus comprising: a detector to determine which portions of image data are blank areas; a finder to identify a symmetrically-located pair of the blank areas; and a designator to designate an area of the image data between the symmetrically-located pair of the blank areas as a candidate region for an image processing function, wherein at least one of the detector, the finder, or the designator is implemented via a logic circuit.

9. An apparatus as defined in claim 8 , wherein the detector is to determine which portions of the image data are blank areas by: detecting edges in the image data; and designating portions of the image data that are edges as blank.

10. An apparatus as defined in claim 8 , wherein the finder is to identify the symmetrically-located pair of the blank areas by: comparing a first dimension of a first one of the blank areas to a second dimension of a second one of the blank areas; comparing a first distance of the first blank area from a center axis of the image data to a second distance of the second blank area from the center axis; and identifying the first and second ones of the blank areas as the symmetrically-located pair if: the first dimension is substantially similar to the second dimension; and the first distance is substantially similar to the second distance.

11. An apparatus as defined in claim 8 , further comprising a filter to: count a number of edges in a space between the blank areas of the symmetrically-located pair; compare the number of edges to a threshold; and discard the symmetrically-located pair when the number of edges does not meet the threshold.

12. An apparatus as defined in claim 8 , wherein the designator is to fit a bounding box around the candidate region.

13. An apparatus as defined in claim 8 , wherein the detector is to determine which portions of the image data are blank areas by: grouping continuous blank pixels into horizontal lines; and grouping ones of the horizontal lines having a similar characteristic.

14. An apparatus as defined in claim 8 , wherein the image processing function is a character recognition operation.

15. A machine-readable storage device comprising instructions that, when executed, cause a machine to at least: detect blank areas in image data; identify a symmetrically-located pair of the blank areas; and designate an area of the image data between the symmetrically-located pair of the blank areas as a candidate region for an image processing function.

16. A machine-readable storage device as defined in claim 15 , wherein the instructions, when executed, cause the machine to detect the blank areas in the image data by: detecting edges in the image data; and designating portions of the image data that are edges as blank.

17. A machine-readable storage device as defined in claim 15 , wherein the instructions, when executed, cause the machine to identify the symmetrically-located pair of the blank areas by: comparing a first dimension of a first one of the blank areas to a second dimension of a second one of the blank areas; comparing a first distance of the first blank area from a center axis of the image data to a second distance of the second blank area from the center axis; and identifying the first and second ones of the blank areas as the symmetrically-located pair if: the first dimension is substantially similar to the second dimension; and the first distance is substantially similar to the second distance.

18. A machine-readable storage device as defined in claim 15 , wherein the instructions, when executed, cause the machine to: count a number of edges in a space between the blank areas of the symmetrically-located pair; compare the number of edges to a threshold; and discard the symmetrically-located pair when the number of edges does not meet the threshold.

19. A machine-readable storage device as defined in claim 15 , wherein the instructions, when executed, cause the machine to fit a bounding box around the candidate region.

20. A machine-readable storage device as defined in claim 15 , wherein the instructions, when executed, cause the machine to detect the blank areas in the image data by: grouping continuous blank pixels into horizontal lines; and grouping ones of the horizontal lines having a similar characteristic.